2
The value proposition
Clinical data from your EHR can be leveraged –providing value outside the walls of the hospital.
Agenda
1. Your clinical data is important for your organization and your patients.
2. Re-using and improving your clinical data is even more important and implicates an investment.
3. Why not monetize this important resource?
4. Who could use this resource?
5. What is the value?
6. EC is showing the way forward!
“The clinical Trial network ERA est arrivé”
7. Practical ways to do it
8. What is in for you! = monetization (ROI)
Which values are important for hospitals & care providers?
Better
patient careImproved
clinical
research
Income
streamEnhanced
reputation
Healthcare Transformation Journey
6
Data gaps
•Missing data elements (e.g.
outcomes)
•RTC’s require details that
may not be routinely
collected
•Coding often only at first
level (e.g. ICD-9) therefore
missing granularity
•80% of info stored as
unstructured data
Strong Incentives to Make R&D More Effective and Efficient
Data quality
•“Longitudinality”
•Coding for administrative
reasons (up-down coding)
•Coding often months after
patient encounter
•Data provenance – who
entered the data?
“Semantics”
•Many standards – many
versions
•Complex care – many HCP’s
involved – many hand-overs
•Need to pool data cross sites
and cross different countries
•Pharma focused on CDISC
Privacy
• Clearly a top priority
• Different interpretations by
country, by region-complex
• Trust
Challenges with re-use
of patient level data
Parallel industry-centric growth in ICTPhysician/Investigator
In some
countries nearly
90% of all
healthcare
records are
digitalPatienthealth
records
Patient Care Data57% of R&D
investment is
within Clinical
Development1
Clinical trial research data
Electronic data capture of
Clinical Trial data
Over 40% of
clinical trial
data are
entered into
health record
and EDC1
Let’s find a market with the same needs so we can mirror our capabilities
R&D cost ever increasing R&D output ever decreasing
The Pharmaceutical Industry in figures. Key data 2012 – efpia report
Pharmaceutical companies have strong incentives to make R&D more effective and efficient
Pharmaceutical companies have strong incentives to make R&D more effective and efficient
857 million research $ are used for the Clinical trial phase per new chemical or biological entity.
A typical clinical trial take approx. 5 years. What if we can shorten this period by providing more complete and better quality clinical data?
With access to data from EHRs, researchers can bring medicines to the market quicker.
Pharmaceutical companies have strong incentives to make R&D more effective and efficient
11
Interoperability Data security,
privacy & ethics Scalability and
sustainability
To address key challenges to enable the re-use of EHR for clinical research
Confidence
in data
InterSystems HealthShare®
• The “gold standard” healthcare technology platform
• Access, aggregate, and normalize data from disparate sources
• InterSystems iKnow™ technology to render unstructured data meaningful and useful
• Embedded analytics capabilities
• High performance – works with transactional data
• Massively scalable – from one hospital to nationwide systems
Ideal for:
• Feasibility of clinical trials
• Patient selection for clinical trials
InterSystems is a data specialist
Existing Initiatives
The era of “networked” clinical trials is upon us
• Life sciences needs the data you already have in your EHR
• They are willing to pay for it
• Are you ready to provide it?
The Innovative Medicines Initiative (IMI) is Europe's largest public-private initiative aiming to speed up the development of better and safer medicines for patients.
IMI supports collaborative research projects and builds networks of industrial and academic experts in order to boost pharmaceutical innovation in Europe.
IMI is a joint undertaking between the European Union and the pharmaceutical industry association EFPIA.
A unique initiative = a real project EHR4CR
• Mandated by IMI
• One of the largest European public/private partnership projects in this area
• 4-year project (2011-2015)
• Extended through 2016
• Budget of € >16m
For further information see
www.ehr4cr.eu or contact
Geert Thienpont (EuroRec)
Electronic Health Records Systems for Clinical Research
Summary
Current medical needs, the growth of targeted therapies and personalized
medicines and escalating R&D costs result in formidable cost pressures on
healthcare systems and the pharmaceutical industry. Clinical research is
also growing in complexity, labour intensity and cost. There is a growing
realization that the development and integration of Electronic
Health Record systems (EHRs) for medical research can:
•Enable substantial efficiency gains
•Make Europe more attractive for R&D investment
•Provide patients better access to innovative medicines and improved
health outcomes.
Universities, research organisations, public bodies & non-profit
eClinical Forum Association, France
European Association of Health Law, University of Edinburgh, UK
European Institute for Health Records, France
European Molecular Biology Laboratory, Germany
European Platform for Patients‘ Oganisations, Science and Industry, Belgium
Friedrich-Alexander University, Erlangen-Nürnberg, Germany
Heinrich-Heine University, Düsseldorf (representing ECRIN), Germany
King‘s College London, UK
Medical University of Warsaw, Poland
National and Kapodistrian University of Athens, Greece
National Institute for Health & Medical Research (INSERM), France
Public Service – Hospitals of Paris, France
Telematics Platform Medical Research Networks, Germany
University College London, UK
University Hospital of Geneva, Switzerland
University of Dundee, UK
University of Edinburgh, UK
University of Glasgow, UK
University of Manchester, UK
University of Rennes 1, France
Westfälische Wilhelms University, Münster, Germany
EFPIA
Amgen NV, Belgium
AstraZeneca AB, Sweden
Bayer Schering Pharma AG, Germany
Eli Lilly, UK
F. Hoffmann-La Roche Ltd, Switzerland
GlaxoSmithKline Research & Development, UK
Janssen Pharmaceutica NV, Belgium
Merck KGaA, Germany
Novartis Pharma AG, Switzerland
Sanofi-Aventis Research and Development, France
Participants
Prof. Dr. Georges de Moor
The EuroRec Institute, Belgium
The EHR4CR platform selection
InterSystems HealthShare enables participation in networked clinical trials
• Integrates data from multiple sources (EHRs, local applications, etc.)
• InterSystems iKnow technologyenables analysis and inclusion ofinformation buried in unstructureddata fields
• Delivers data (in a variety of formats) to a trusted third party
A 2ND unique initiative = a second real project EMIF
• Mandated by IMI
• One of the largest European public/private partnership projects in this area
• 4-year project (2013-2015)
• Extended through 2016
• Budget of € >16m
• Difference with EHR4CR= data
not coming only from EHR’sFor further information see
www.emif.eu or contact
Bart VanNieuwenhuysse
(Janssen Pharma)
Better quality EHR data
Improved monitoring, performance benchmarking, reporting and
management (e.g. reimbursement coding)
Drives optimization of patient care and improved efficiencies
Better patient care
Improved clinical
research
Income stream
Enhanced reputation
Initiatives like EHR4CR and EMIF create value for hospitals...
10
01
011
01
01
Improved access to health record data will speed up
• protocol design
• patient recruitment
• data capture
• safety reporting
… and pharmaceutical companies
A win for all stakeholders is critical
Pharma,
academia,
CROs
Hospitals
Health
authoritie
s
Health
communit
y/
governme
nts
and EU
Patients
Some use cases
InterSystems iKnow Technology
• Unique technology for text exploration and analysis
• “Bottom-up” approach eliminates the need for pre-defined libraries
• Fully integrated with InterSystems DeepSee™
embedded analytics technology
• Connects to third-party tools or applications via an API or standard SQL
27
Examples of the iKnow Text Analytics Breakthroughs in Action
Intelligent EHR
Navigation
PopulationScreening
PredictingPatientsat Risk
PatientCohort Identification
and Selection
28
Intelligent EHR Navigation
No time to read through all clinical notes.
Risk of missing the important needle in the haystack.
29
Intelligent EHR
Navigation
30
Intelligent EHR
Navigation
31
Intelligent EHR
Navigation
Patient Cohort Identification and Selection
Need access to real-world data
Structured data alone not rich enough
Selection criteria should not be based on guesswork
33
Acta Oncol. 2012 Sep 5.
Metformin use and improved response to therapy in esophageal adenocarcinoma.
Skinner HD, McCurdy MR, Echeverria AE, Lin SH,
Welsh JW, O'Reilly MS, Hofstetter WL, Ajani JA, Komaki R,
Cox JD, Sandulache VC, Myers JN, Guerrero TM
Department of Radiation Oncology, The University of Texas
MD Anderson Cancer Center, Houston, Texas, USA
33
Identify Patients with a Certain Condition
PatientCohort Identification
and Selection
34
Head & Neck CancerMetformin Diabetic
34
PatientCohort Identification
and Selection
35
0 in metadata Forms in notes
Partially in metadataForms in notes
All in metadata
35
Head & Neck CancerMetformin Diabetic
PatientCohort Identification
and Selection
36
Identify Patients with a Certain Condition
36
PatientCohort Identification
and Selection
37
Identify Patients with a Certain ConditionPatient
Cohort Identificationand Selection
Predicting Patients at Risk
Shift from reactive to pro-active medicine.
Need predictive models based on all the data.
39
Driving Actions with Real World Predictive Models
Early Detection of
Hepatitis C
Isolation
Sepsis
Deleria
Readmission in
psychiatric care
PredictingPatientsat Risk
40
Early Detection of IsolationPredictingPatientsat Risk
41
1. Crisis center
2. IBS
3. Consultation
4. Medication
5. Examination
6. Kcap
7. Suicide Risk
Early Detection to Prevent Isolation
8. Assessment
9. Bad
10. Not possible
11. Voluntary admission
12. Drugs
13. appointments
PredictingPatientsat Risk
• Injecting Drug User (IDU)
• HIV
• Country of origin: HCV prevalence > 2%
• High ethnic mix area
• LFT: ALT more the
• Transfusion before 1992
• Piercing
• Acupuncture
• Tattoo
• Men having sex with men (MSM)
• Household & sex partners of Hep carriers
• Prison stay
Identifying Hepatitis C “At Risk” Patients
HCV Risk Group Drivers
• Alert and outcome “score”
• Clinical support
– Guidance on additional questions
– Testing recommendation
• Links to knowledge base
Positive Risk Alert
Algorithm CriteriaPatient Database Risk Indicator Flag Hep C Test
42
PredictingPatientsat Risk
43
Healthcare Journey
Prevention of
Hepatitis C
Isolation
Sepsis
Delerium
Personalized Medicine
Cancer therapy
Reactive Proactive
PredictingPatientsat Risk
Population Screening
Too many records to sort through manually
Gaps in structured data
Risk of missing an at-risk patient
45
iknow at Cancer RegistriesPopulationScreening
46
Faster time-to-market
Accurate test patients
Less manual work
And more
Conclusion:The Value of iKnow for Clinical Practice and Medical Research
Conclusions
• All care providers have a very important asset: clinical data
• All pharmaceutical companies need this clinical data to do their research work.
• We offer rapid & simple integration, normalization, aggregation, and analysis of structured & unstructured data. Data becomes high quality information.
• Better clinical data will have a direct impact on the outcome of clinical trials
• Better outcome of the patient selection phase will have a direct impact on the duration
of the clinical trial.
• Better outcome of clinical trials and shorter clinical trials will have a direct impact on
the cost of research...
• and even more importantly, on the time-to-market of the medicine, thus providing a
competitive advantage.
Herman Roelandts
Country Sales Manager Benelux
+32 478 20 60 61